Papers › TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action...

TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential

23 Apr 2023arXiv:2304.11631archive 2025-07-28

Dongjingdin Liu, Pengpeng Chen, Miao Yao, Yijing Lu, Zijie Cai, Yuxin Tian

Skeleton-based action recognition has achieved remarkable results in human action recognition with the development of graph convolutional networks (GCNs). However, the recent works tend to construct complex learning mechanisms with redundant training and exist a bottleneck for long time-series. To solve these problems, we propose the Temporal-Spatio Graph ConvNeXt (TSGCNeXt) to explore efficient learning mechanism of long temporal skeleton sequences. Firstly, a new graph learning mechanism with simple structure, Dynamic-Static Separate Multi-graph Convolution (DS-SMG) is proposed to aggregate features of multiple independent topological graphs and avoid the node information being ignored during dynamic convolution. Next, we construct a graph convolution training acceleration mechanism to optimize the back-propagation computing of dynamic graph learning with 55.08\% speed-up. Finally, the TSGCNeXt restructure the overall structure of GCN with three Spatio-temporal learning modules,efficiently modeling long temporal features. In comparison with existing previous methods on large-scale datasets NTU RGB+D 60 and 120, TSGCNeXt outperforms on single-stream networks. In addition, with the ema model introduced into the multi-stream fusion, TSGCNeXt achieves SOTA levels. On the cross-subject and cross-set of the NTU 120, accuracies reach 90.22% and 91.74%.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

vvhj/tsgcnext officialmentioned in papermentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action RecognitionGraph LearningSkeleton Based Action RecognitionTemporal Action LocalizationTime Series

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Skeleton Based Action Recognition NTU RGB+D 120 TSGCNeXt Accuracy (Cross-Setup) 91.7 #8 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 TSGCNeXt Accuracy (Cross-Subject) 90.2 #8 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 TSGCNeXt Ensembled Modalities 4 #8 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 TSGCNeXT Accuracy (Cross-Setup) 90.3 #23 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 TSGCNeXT Accuracy (Cross-Subject) 89.1 #23 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 TSGCNeXT Ensembled Modalities 4 #23 of 83 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ConvNeXtConvolutionGCN

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections